Thank you for this PR!

However, this option seems a bit complicated and confusing. Please tell me why #2270's skip_image_resolution is not enough.

min_orig_resolution is exactly your skip_image_resolution but I renamed it because I think min_orig_resolution is more self-evident.

I can rename it back to skip_image_resolution and remove max_orig_resolution if you think that's better.

The code is indeed more complicated than what I thought at first, but this is the best way I (and AI tools I use) can find to implement:

1. The filter using original resolution, which can be done only after we know the original resolution in make_buckets
2. Make regularization images work correctly with the filter
3. Make conditioning images work correctly with the filter

Thanks for the explanation, I understand now.

skip_image_resolution explicitly states that images of that resolution will not be included, but I don't think min_orig_resolution explicitly states whether they will be included or not.

I'll try to find out if there's a simpler way to implement this.

Thank you for update!

I think we could simply filter images with the following code.
Note that skip_image_resolution should be a tuple, just like resolution.

                            size_set_count += 1
                    logger.info(f"set image size from cache files: {size_set_count}/{len(img_paths)}")

            # from here
            if self.skip_image_resolution is not None:
                filtered_img_paths = []
                filtered_sizes = []
                skip_image_area = self.skip_image_resolution[0] * self.skip_image_resolution[1]
                for img_path, size in zip(img_paths, sizes):
                    if size is None:  # no latents cache file, get image size by reading image file (slow)
                        size = self.get_image_size(img_path)
                    if size[0] * size[1] <= skip_image_area:
                        continue
                    filtered_img_paths.append(img_path)
                    filtered_sizes.append(size)
                img_paths = filtered_img_paths
                sizes = filtered_sizes
                # add some logging here
            # to here

            # We want to create a training and validation split. This should be improved in the future
            # to allow a clearer distinction between training and validation. This can be seen as a

In FineTuningDataset, we can use the image size from the metadata.

Yes this makes the PR simpler. I've moved the filtering from make_buckets to __init__.

Thank you for update! I will create a test dataset and review/test this sooner.

I've merged this and added a documentation for this feature. I'm sorry it took so long to merge. Thank you for this PR again!